Radar sparse imaging method based on quantum machine learning

Abstract

The invention discloses a radar sparse imaging method based on quantum machine learning, which specifically comprises the steps of: 1, exploring a well-posedness equation set of an observation model according to the ill-posedness of the radar sparse imaging observation model on the basis of analyzing the constraint conditions of a quantum linear equation set solving algorithm (HHL algorithm), and constructing a well-posedness linear equation set of the observation model meeting the constraint conditions of the HHL algorithm; and 2, by aiming at the well-posedness linear equation set approximate to the observation model, deriving quantum state evolution solved by the well-posedness linear equation set according to the coefficient matrix eigenvalue, the condition number and the like of the well-posedness linear equation set in combination with the basic framework of the HHL algorithm, and constructing a corresponding quantum line to realize radar sparse imaging based on quantum machine learning. According to the invention, a quantum machine learning algorithm with exponential magnitude acceleration performance is combined with a radar sparse imaging technology, and the real-time imaging processing capability of radar sparse imaging is greatly improved.

Description

technical field [0001] The invention belongs to the cross technical field of quantum computing and radar signal processing, and relates to a radar sparse imaging method based on quantum machine learning. Background technique [0002] Synthetic Aperture Radar (SAR) and Inverse Synthetic Aperture Radar (ISAR) microwave imaging play a pivotal role in military and civilian fields such as terrain mapping, ocean monitoring, and target recognition due to their high-resolution performance. Due to the need for broadband signals and long coherent processing intervals in the process of high-resolution image and large-scale scene recovery, a large amount of radar echo data is collected, which brings great challenges to data collection and storage. To solve this problem, Compressed Sensing (CS) theory is widely used in SAR / ISAR sparse imaging. However, although the sparse-driven radar imaging method can improve the radar imaging performance under echo undersampling conditions, it usuall...

AI Technical Summary

Problems solved by technology

However, in order to realize the real-time imaging processing of radar sparse imaging in large scenes and high resolution, it still needs long-term efforts

Images